Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    framework, castle, Pull Request, version, Llama

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ेक्स
    0.84
     Divid
    0.82
    ＮＡ
    0.81
    Div
    0.80
    て
    0.80
    डी
    0.79
    イ
    0.79
    ان
    0.78
    Nama
    0.77
     Administ
    0.77
    POSITIVE LOGITS
    rencies
    0.79
    ژگی
    0.79
    polling
    0.78
    me
    0.77
    pose
    0.74
    ামুটি
    0.74
    ాలి
    0.73
     poop
    0.72
    чкой
    0.71
     chickpeas
    0.71
    Act Density 0.001%

    No Known Activations